Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to the location or origin where something is made

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "in" along with related contextual terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Bey
    -0.77
     commenters
    -0.70
    SPONSORED
    -0.69
    worthy
    -0.66
    catentry
    -0.66
     claimants
    -0.65
    isSpecialOrderable
    -0.65
    hai
    -0.65
    inventoryQuantity
    -0.63
    yrs
    -0.63
    POSITIVE LOGITS
     accordance
    1.13
     conjunction
    1.07
     situ
    1.04
     vitro
    1.00
     earnest
    0.93
     tandem
    0.92
     unison
    0.89
     lieu
    0.87
    organic
    0.86
    ertodd
    0.85
    Act Density 0.261%

    No Known Activations